Classifying Causal Structures: Ascertaining when Classical Correlations are Constrained by Inequalities

• URL: http://arxiv.org/abs/2308.02380v1
• Date: Fri, 4 Aug 2023 15:23:55 GMT
• Title: Classifying Causal Structures: Ascertaining when Classical Correlations are Constrained by Inequalities
• Authors: Shashaank Khanna, Marina Maciel Ansanelli, Matthew F. Pusey, and Elie Wolfe
• Abstract summary: We develop methods for detecting causal scenarios that impose inequality constraints versus those which do not. Many scenarios with exclusively equality constraints can be detected via a condition articulated by Henson, Lal and Pusey. We are able to resolve all but three causal scenarios, providing evidence that the HLP condition is, in fact, exhaustive.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The classical causal relations between a set of variables, some observed and some latent, can induce both equality constraints (typically conditional independences) as well as inequality constraints (Instrumental and Bell inequalities being prototypical examples) on their compatible distribution over the observed variables. Enumerating a causal structure's implied inequality constraints is generally far more difficult than enumerating its equalities. Furthermore, only inequality constraints ever admit violation by quantum correlations. For both those reasons, it is important to classify causal scenarios into those which impose inequality constraints versus those which do not. Here we develop methods for detecting such scenarios by appealing to d-separation, e-separation, and incompatible supports. Many (perhaps all?) scenarios with exclusively equality constraints can be detected via a condition articulated by Henson, Lal and Pusey (HLP). Considering all scenarios with up to 4 observed variables, which number in the thousands, we are able to resolve all but three causal scenarios, providing evidence that the HLP condition is, in fact, exhaustive.

Related papers

• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time. We show that enforcing a causal constraint often reduces the disparity between demographic groups. We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Tsirelson bounds for quantum correlations with indefinite causal order [4.162019309587634]
  We provide a general method for bounding the violation of arbitrary causal inequalities. We prove that the maximum violation is generally smaller than the algebraic maximum. Surprisingly, we find that the algebraic maximum of arbitrary causal inequalities can be achieved by a new type of processes.
  arXiv  Detail & Related papers  (2024-03-05T08:07:10Z)
• On Regularization and Inference with Label Constraints [62.60903248392479]
  We compare two strategies for encoding label constraints in a machine learning pipeline, regularization with constraints and constrained inference. For regularization, we show that it narrows the generalization gap by precluding models that are inconsistent with the constraints. For constrained inference, we show that it reduces the population risk by correcting a model's violation, and hence turns the violation into an advantage.
  arXiv  Detail & Related papers  (2023-07-08T03:39:22Z)
• Nonclassicality in correlations without causal order [0.0]
  We propose a notion of classicality for correlations--termed deterministic consistency--that goes beyond causal inequalities. A key contribution of this work is an explicit nonclassicality witness that goes beyond causal inequalities.
  arXiv  Detail & Related papers  (2023-07-05T18:04:16Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Remarks on the use of objective probabilities in Bell-CHSH inequalities [0.0]
  We explore the axioms which can be deduced from two widely used objetive probability theories: frequentism and propensities. One of the strongest objections in the deduction of one version of Bell inequalities goes about the probability space. It is shown that frequentism rejects the possibility of using counterfactual situations, while long-run propensities allow their use.
  arXiv  Detail & Related papers  (2022-02-16T21:59:52Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• A Weaker Faithfulness Assumption based on Triple Interactions [89.59955143854556]
  We propose a weaker assumption that we call $2$-adjacency faithfulness. We propose a sound orientation rule for causal discovery that applies under weaker assumptions.
  arXiv  Detail & Related papers  (2020-10-27T13:04:08Z)
• Generalizing optimal Bell inequalities [0.0]
  Bell inequalities are central tools for studying nonlocal correlations and their applications in quantum information processing. We develop a method to characterize Bell inequalities under constraints, which may be given by symmetry or other linear conditions. This allows to search systematically for generalizations of given Bell inequalities to more parties.
  arXiv  Detail & Related papers  (2020-05-18T13:11:02Z)
• On the three types of Bell's inequalities [0.0]
  I will argue that the violation of Bell's inequalities has different meanings in the three cases. In the first case it rules out the interpretation of certain numbers as probabilities of events. In the second case it rules out a common causal explanation of conditional correlations of certain events. In the third case the violation neither rules out the interpretation of these numbers as probabilities of events nor a common causal explanation of the correlations between these events.
  arXiv  Detail & Related papers  (2020-04-29T10:11:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.